This paper describes the year 2000 BBN Byblos Mandarin large vocabulary conversational speech recognition (LVCSR) system, the winning (and only) Mandarin system from the Spring 2000 Hub-5 evaluation sponsored by NIST. We first outline the training and decoding procedures used in the system, and describe the performance of the system used in the evaluation. We then describe the effect of several features that were not in the evaluation system but have been added since, including Jacobian compensated Vocal Tract Length Normalization (VTLN), system combination, a higher number of system parameters, and additional training data. Together these give an additional 5.4% relative improvement on character error rate (CER) from the evaluation system.
Cite as: Shu, H., Wooters, C., Kimball, O., Colthurst, T., Richardson, F., Matsoukas, S., Gish, H. (2000) The BBN Byblos 2000 conversational Mandarin LVCSR system. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 2, 1007-1010, doi: 10.21437/ICSLP.2000-442
@inproceedings{shu00_icslp,
author={Han Shu and Chuck Wooters and Owen Kimball and Thomas Colthurst and Fred Richardson and Spyros Matsoukas and Herbert Gish},
title={{The BBN Byblos 2000 conversational Mandarin LVCSR system}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 2, 1007-1010},
doi={10.21437/ICSLP.2000-442}
}